liveBook · Manning

Auto memory

As explained in Designing AI Agents

Claude Code's agent-authored memory facility, which loads selected indexed content at session start and makes detailed topic files available for retrieval.

Auto memory lets Claude Code preserve model-written project notes across sessions. A small project index enters the prompt at session start, while detailed topic files can be retrieved as needed. This structure provides continuity without putting every detailed note into the prompt. section 4.1.3 section 4.2.2

The notes are candidate context, not verified rules. Keep their model authorship distinguishable from human-owned instructions so their provenance and conflicts can be assessed. An inferred note may be revised or retired automatically; a hard rule requires its human owner. section 4.2.2

Auto memory can influence the model’s next choice, but it cannot enforce a tool boundary. Use managed settings, sandbox restrictions, or hooks for rules that must not be bypassed. A model-written note should not silently rewrite a managed policy or human-owned project rule. section 4.1.3 section 4.2.2

Remembering a failed approach

A project note about a failed approach can serve as candidate failure memory in a later session. It is still a model-authored claim, not a verified lesson. A dedicated Failure Journal can make capture explicit and link candidate diagnoses to raw evidence, with another check before publication. section 4.5.2

Table 4.3 Claude Code persistent-context mechanisms and enforcement boundary
Mechanism
 
Writer or owner
 
Scope and load behavior
 
Enforces behavior?
 
Managed instruction file
Organization administrator
Organization context
 
No; use managed settings or sandbox policy
 
User memory
Human user
 
User context across projects
 
No; prompt context
 
Project memory
Project team
Repository context via source control
No; prompt context
 
Project rules
Project team
Topic or path-scoped context
 
No; prompt context
 
Local project memory
Human user
 
Private context for one project
 
No; prompt context
 
Auto memory
Model
 
Project index plus retrieved topic detail
 
No; model-written context
 

Compare auto memory’s model ownership and project scope with other persistent-context mechanisms and their enforcement boundaries. section 4.1.3

How Designing AI Agents covers it

How deep it goes
Explains the index-and-topic-file structure, ownership, retention, and enforcement boundary without specifying an implementation procedure.
Examples
Uses a note about a failed approach to illustrate candidate failure memory and comparison with a Failure Journal.
What you can do after
Evaluate auto memory as candidate context rather than an authoritative policy or enforcement mechanism.
How it connects
Connects auto memory to instruction files, sandbox restrictions, hooks, and failure memory.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Designing AI Agents. The section links point to the parts of the book it draws on.